LoSAM通过局部搜索实现混合机制下的高效因果发现
LoSAM: Local Search in Additive Noise Models with Mixed Mechanisms and General Noise for Global Causal Discovery
- 基于新增因果子结构进行根与叶的识别，实现自顶向下拓扑排序
- 在所有混合机制设置下表现优于现有方法，具备多项式时间复杂度
- 适用于真实世界数据，支持一般噪声分布与混合因果机制
从观测数据中推断因果关系在实验成本高或不可行时至关重要。加性噪声模型（ANMs）可唯一识别有向无环图（DAG），但现有高效样本的ANM方法常依赖对数据生成过程的严格假设，限制了其在真实场景的应用。本文提出局部搜索加性噪声模型（LoSAM），一种在混合因果机制与一般噪声分布下学习唯一DAG的拓扑排序方法。我们引入新的因果子结构及根、叶判别准则，实现高效的自顶向下学习。理论证明其渐近一致性和多项式时间复杂度，确保可扩展性与样本效率。在合成数据和真实世界数据上测试表明，LoSAM在所有混合机制设置下均达到当前最优性能。
原文摘要 · Abstract (English)
Inferring causal relationships from observational data is crucial when experiments are costly or infeasible. Additive noise models (ANMs) enable unique directed acyclic graph (DAG) identification, but existing sample-efficient ANM methods often rely on restrictive assumptions on the data generating process, limiting their applicability to real-world settings. We propose local search in additive noise models, LoSAM, a topological ordering method for learning a unique DAG in ANMs with mixed causal mechanisms and general noise distributions. We introduce new causal substructures and criteria for identifying roots and leaves, enabling efficient top-down learning. We prove asymptotic consistency and polynomial runtime, ensuring scalability and sample efficiency. We test LoSAM on synthetic and real-world data, demonstrating state-of-the-art performance across all mixed mechanism settings.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。